DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Yang, Hyun Seung | - |
dc.contributor.advisor | 양현승 | - |
dc.contributor.author | Arthur, Meyer | - |
dc.date.accessioned | 2018-06-20T06:24:27Z | - |
dc.date.available | 2018-06-20T06:24:27Z | - |
dc.date.issued | 2017 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=718729&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/243459 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2017.8,[iv, 56 p. :] | - |
dc.description.abstract | Salient regions are known to be important for the human visual system. In computer vision, the associated saliency detection task has received an increasing interest in the recent years. Despite the substantial progresses made following the introduction of deep learning approaches, many challenging issues remain. Indeed these methods often process local regions within images separately and as a result have difficulties capturing global patterns. In addition saliency maps are often blurry around the boundary of the salient object. To address these issues, we propose a convolutional autoencoder which first extracts the information contained in input images using a convolutional network (encoder) before generating output saliency maps using a deconvolution network (decoder). Our network operates on whole image directly so that global patterns are captured with ease. To reduce blurriness in the output we add direct connections between the encoder and the decoder. Finally the inclusion of a novel contrast penalty term helps further improve the sharpness of the output, especially around the edges of salient objects. We compare our method with six other state-of-the-art algorithms on three widely used benchmarks, where it shows equivalent performance. We also conduct four experiments to better understand how encoding and decoding are done. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Convolutional Autoencoder▼aSaliency Detection▼aDeconvolution Network | - |
dc.subject | Edge Contrast Penalty | - |
dc.subject | 컨벌루션 오토인코더▼a영역 검출▼a디컨벌루저널 신경망▼a에지 대비 패널티▼a딥 러닝 | - |
dc.title | Convolutional autoencoder for saliency dectection | - |
dc.title.alternative | 선명한 saliency map을 생성하기 위한 에지 대비 패널티 기반의 컨벌루션 오토인코더 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.title.subtitle | enforcing sharp boundary using edge contrast penalty | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.